基于FCM和形变模型的左心室MRI自动分割

形变模型近年来被广泛应用于医学磁共振图像的分析。该类模型是一种交互式的分割方法,需要人工设定初始曲线,不仅浪费了时间,而且分割结果也很大程度上受到人工初始化的影响。为此,针对左心室MRI内壁的分割,给出一种多指标FCM算法,在该算法基础上自动定位左心室区域,构造初始曲线,并改进水平集方法的速度函数。在新的形变模型自动分割框架下,整个左心室分割过程变为全自动进行,不需要人工干预。实验结果表明了该方法不仅有效和易于实现,且具有较强的鲁棒性。

Automatic Segmentation for Left Ventricle MRI Based on FCM Algorithm and Deformable Models

Deformable models,including snake models and level set method is popular used in the segmentation of cardiac MRI and they can get much better result than classical segmentation method.The deformable model is an interactive method,it need human initialize a original curve.This process not only waste much time,but also strongly impact the segmentation result.This paper proposes a new automatic segmentation framework of deformable models for the segmentation of left ventricle in cardiac MRI.At first improves proposed a multi-indexes fuzzy C-means clustering(FCM),then detects the region of left ventricle in cardiac MRI automatically and constructs a original curve based on the improved FCM,at last improves the classic velocity of Level Set method.In this framework,the whole segmentation process is automatic.The experiments on the tagged left ventricle Magnetic Resonance Images show the effective and robust of this method,and easy to implement.